Commit
•
5ec6583
1
Parent(s):
b4c018c
Update tokenizer_config.json
Browse files- tokenizer_config.json +4 -2
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -110,7 +112,7 @@
|
|
| 110 |
"pad_token": null,
|
| 111 |
"sp_model_kwargs": {},
|
| 112 |
"spaces_between_special_tokens": false,
|
| 113 |
-
"tokenizer_class": "
|
| 114 |
"unk_token": "<unk>",
|
| 115 |
"use_default_system_prompt": false,
|
| 116 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": ["tokenization_minicpm.MiniCPMTokenizer", null]
|
| 4 |
+
},
|
| 5 |
"add_bos_token": true,
|
| 6 |
"add_eos_token": false,
|
|
|
|
| 7 |
"added_tokens_decoder": {
|
| 8 |
"0": {
|
| 9 |
"content": "<unk>",
|
|
|
|
| 112 |
"pad_token": null,
|
| 113 |
"sp_model_kwargs": {},
|
| 114 |
"spaces_between_special_tokens": false,
|
| 115 |
+
"tokenizer_class": "MiniCPMTokenizer",
|
| 116 |
"unk_token": "<unk>",
|
| 117 |
"use_default_system_prompt": false,
|
| 118 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|